SherbyNet - /page/wikibook/entry.mu

Micron Document

`:top

`!Recursive partitioning`! is a `F33f`_`[statistical`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Statistics]`_`f method for `F33f`_`[multivariable analysis`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Multivariable_analysis]`_`f.`:cite-ref-isbn0-412-04841-8-1-0[`F5bf`_`[1`#cite-note-isbn0-412-04841-8-1]`_`f] Recursive partitioning creates a `F33f`_`[decision tree`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Decision_tree_learning]`_`f that strives to correctly classify members of the population by splitting it into sub-populations based on several dichotomous `F33f`_`[independent variables`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Independent_variable]`_`f. The process is termed `F33f`_`[recursive`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Recursion]`_`f because each sub-population may in turn be split an indefinite number of times until the splitting process terminates after a particular stopping criterion is reached.

Recursive partitioning methods have been developed since the 1980s. Well known methods of recursive partitioning include Ross Quinlan's `F33f`_`[ID3 algorithm`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=ID3_algorithm]`_`f and its successors, `F33f`_`[C4.5`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=C4.5]`_`f and `F33f`_`[C5.0`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=C5.0]`_`f and `F33f`_`[Classification and Regression Trees`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Decision_tree_learning]`_`f (CART). `F33f`_`[Ensemble learning`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Ensemble_learning]`_`f methods such as `F33f`_`[Random Forests`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Random_forest]`_`f help to overcome a common criticism of these methods – their vulnerability to `F33f`_`[overfitting`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Overfitting]`_`f of the data – by employing different algorithms and combining their output in some way.

This article focuses on recursive partitioning for medical `F33f`_`[diagnostic`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Diagnostic]`_`f tests, but the technique has far wider applications. See `F33f`_`[decision tree`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Decision_tree_learning]`_`f.

As compared to regression analysis, which creates a formula that health care providers can use to calculate the probability that a patient has a disease, recursive partition creates a rule such as 'If a patient has finding x, y, or z they probably have disease q'.

A variation is 'Cox linear recursive partitioning'.`:cite-ref-pmid6501544-2-0[`F5bf`_`[2`#cite-note-pmid6501544-2]`_`f]

>>Contents

• `F0af`_`[Advantages and disadvantages`#advantages-and-disadvantages]`_`f

• `F0af`_`[Examples`#examples]`_`f

• `F0af`_`[See also`#see-also]`_`f

• `F0af`_`[References`#references]`_`f

-─

>>Advantages and disadvantages

Compared to other multivariable methods, recursive partitioning has advantages and disadvantages.

• Advantages are:

• Generates clinically more intuitive models that do not require the user to perform calculations.`:cite-ref-pmid16149128-3-0[`F5bf`_`[3`#cite-note-pmid16149128-3]`_`f]

• Allows varying prioritizing of misclassifications in order to create a decision rule that has more `F33f`_`[sensitivity`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Sensitivity_(tests)]`_`f or `F33f`_`[specificity`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Specificity_(tests)]`_`f.`:cite-ref-pmid6501544-2-1[`F5bf`_`[2`#cite-note-pmid6501544-2]`_`f]

• May be more accurate.`:cite-ref-pmid9790741-4-0[`F5bf`_`[4`#cite-note-pmid9790741-4]`_`f]

• Disadvantages are:

• Does not work well for continuous variables`:cite-ref-pmid16482368-5-0[`F5bf`_`[5`#cite-note-pmid16482368-5]`_`f]

• May overfit data.

>>Examples

Examples are available of using recursive partitioning in research of diagnostic tests.`:cite-ref-pmid15687312-6-0[`F5bf`_`[6`#cite-note-pmid15687312-6]`_`f]`:cite-ref-pmid11597285-7-0[`F5bf`_`[7`#cite-note-pmid11597285-7]`_`f]`:cite-ref-pmid10891517-8-0[`F5bf`_`[8`#cite-note-pmid10891517-8]`_`f]`:cite-ref-pmid3060613-9-0[`F5bf`_`[9`#cite-note-pmid3060613-9]`_`f]`:cite-ref-pmid8594242-10-0[`F5bf`_`[10`#cite-note-pmid8594242-10]`_`f]`:cite-ref-pmid7110205-11-0[`F5bf`_`[11`#cite-note-pmid7110205-11]`_`f] Goldman used recursive partitioning to prioritize `F33f`_`[sensitivity`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Sensitivity_(tests)]`_`f in the diagnosis of `F33f`_`[myocardial infarction`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Myocardial_infarction]`_`f among patients with chest pain in the emergency room.`:cite-ref-pmid7110205-11-1[`F5bf`_`[11`#cite-note-pmid7110205-11]`_`f]

>>See also

• `F33f`_`[Decision tree learning`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Decision_tree_learning]`_`f

>>References

`:cite-note-isbn0-412-04841-8-1`!1.`! `F0af`_`[↑`#cite-ref-isbn0-412-04841-8-1-0]`_`f `:citerefbreiman-leo1984`aBreiman, Leo (1984). `*Classification and Regression Trees`*. Boca Raton: Chapman & Hall/CRC. `F33f`_`[ISBN`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=ISBN_(identifier)]`_`f 978-0-412-04841-8.

`:cite-note-pmid6501544-2`!2.`! `F0af`_`[↑`#cite-ref-pmid6501544-2-0]`_`f `:citerefcookgoldman1984`aCook EF, Goldman L (1984). "Empiric comparison of multivariate analytic techniques: advantages and disadvantages of recursive partitioning analysis". `*Journal of Chronic Diseases`*. `!37`! (9–10): 721–31. `F33f`_`[doi`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Doi_(identifier)]`_`f:10.1016/0021-9681(84)90041-9. `F33f`_`[PMID`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=PMID_(identifier)]`_`f 6501544.

`:cite-note-pmid16149128-3`!3.`! `F0af`_`[↑`#cite-ref-pmid16149128-3-0]`_`f `:citerefjameswhitekraemer2005`aJames KE, White RF, Kraemer HC (2005). "Repeated split sample validation to assess logistic regression and recursive partitioning: an application to the prediction of cognitive impairment". `*Statistics in Medicine`*. `!24`! (19): 3019–35. `F33f`_`[doi`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Doi_(identifier)]`_`f:10.1002/sim.2154. `F33f`_`[PMID`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=PMID_(identifier)]`_`f 16149128.

`:cite-note-pmid9790741-4`!4.`! `F0af`_`[↑`#cite-ref-pmid9790741-4-0]`_`f `:citerefkattanhessbeck1998`aKattan MW, Hess KR, Beck JR (1998). "Experiments to determine whether recursive partitioning (CART) or an artificial neural network overcomes theoretical limitations of Cox proportional hazards regression". `*Comput. Biomed. Res`*. `!31`! (5): 363–73. `F33f`_`[doi`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Doi_(identifier)]`_`f:10.1006/cbmr.1998.1488. `F33f`_`[PMID`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=PMID_(identifier)]`_`f 9790741.

`:cite-note-pmid16482368-5`!5.`! `F0af`_`[↑`#cite-ref-pmid16482368-5-0]`_`f `:citerefleeumleemun2006`aLee JW, Um SH, Lee JB, Mun J, Cho H (2006). "Scoring and staging systems using cox linear regression modeling and recursive partitioning". `*Methods of Information in Medicine`*. `!45`! (1): 37–43. `F33f`_`[doi`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Doi_(identifier)]`_`f:10.1055/s-0038-1634034. `F33f`_`[PMID`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=PMID_(identifier)]`_`f 16482368.

`:cite-note-pmid15687312-6`!6.`! `F0af`_`[↑`#cite-ref-pmid15687312-6-0]`_`f `:citereffonarowadamsabrahamyancy2005`aFonarow GC, Adams KF, Abraham WT, Yancy CW, Boscardin WJ (2005). "Risk stratification for in-hospital mortality in acutely decompensated heart failure: classification and regression tree analysis". `*JAMA`*. `!293`! (5): 572–80. `F33f`_`[doi`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Doi_(identifier)]`_`f:10.1001/jama.293.5.572. `F33f`_`[PMID`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=PMID_(identifier)]`_`f 15687312.

`:cite-note-pmid11597285-7`!7.`! `F0af`_`[↑`#cite-ref-pmid11597285-7-0]`_`f `:citerefstiellwellsvandemheen2001`aStiell IG, Wells GA, Vandemheen KL, et al. (2001). "The Canadian C-spine rule for radiography in alert and stable trauma patients". `*JAMA`*. `!286`! (15): 1841–8. `F33f`_`[doi`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Doi_(identifier)]`_`f:10.1001/jama.286.15.1841. `F33f`_`[PMID`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=PMID_(identifier)]`_`f 11597285.

`:cite-note-pmid10891517-8`!8.`! `F0af`_`[↑`#cite-ref-pmid10891517-8-0]`_`f `:citerefhaydelprestonmillsluber2000`aHaydel MJ, Preston CA, Mills TJ, Luber S, Blaudeau E, DeBlieux PM (2000). "Indications for computed tomography in patients with minor head injury". `*N. Engl. J. Med`*. `!343`! (2): 100–5. `F33f`_`[doi`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Doi_(identifier)]`_`f:10.1056/NEJM200007133430204. `F33f`_`[PMID`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=PMID_(identifier)]`_`f 10891517.

`:cite-note-pmid3060613-9`!9.`! `F0af`_`[↑`#cite-ref-pmid3060613-9-0]`_`f `:citerefedworthyzatarainmcshanebloch1988`aEdworthy SM, Zatarain E, McShane DJ, Bloch DA (1988). "Analysis of the 1982 ARA lupus criteria data set by recursive partitioning methodology: new insights into the relative merit of individual criteria". `*J. Rheumatol`*. `!15`! (10): 1493–8. `F33f`_`[PMID`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=PMID_(identifier)]`_`f 3060613.

`:cite-note-pmid8594242-10`!10.`! `F0af`_`[↑`#cite-ref-pmid8594242-10-0]`_`f `:citerefstiellgreenbergwells1996`aStiell IG, Greenberg GH, Wells GA, et al. (1996). "Prospective validation of a decision rule for the use of radiography in acute knee injuries". `*JAMA`*. `!275`! (8): 611–5. `F33f`_`[doi`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Doi_(identifier)]`_`f:10.1001/jama.275.8.611. `F33f`_`[PMID`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=PMID_(identifier)]`_`f 8594242.

`:cite-note-pmid7110205-11`!11.`! `F0af`_`[↑`#cite-ref-pmid7110205-11-0]`_`f `:citerefgoldmanweinbergweisberg1982`aGoldman L, Weinberg M, Weisberg M, et al. (1982). "A computer-derived protocol to aid in the diagnosis of emergency room patients with acute chest pain". `*N. Engl. J. Med`*. `!307`! (10): 588–96. `F33f`_`[doi`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=Doi_(identifier)]`_`f:10.1056/NEJM198209023071004. `F33f`_`[PMID`:/page/wikibook/entry.mu`zim=wikipedia_en_all_nopic_2025-08.zim|entry_path=PMID_(identifier)]`_`f 7110205.

`c`F0af`_`[↑ Back to top`#top]`_`f`a